Files
claw-code/src/main.py

388 lines
16 KiB
Python
Raw Normal View History

from __future__ import annotations
import argparse
from .bootstrap_graph import build_bootstrap_graph
from .command_graph import build_command_graph
from .commands import execute_command, get_command, get_commands, render_command_index
from .direct_modes import run_deep_link, run_direct_connect
from .parity_audit import run_parity_audit
from .permissions import ToolPermissionContext
from .port_manifest import build_port_manifest
from .query_engine import QueryEnginePort
from .remote_runtime import run_remote_mode, run_ssh_mode, run_teleport_mode
from .runtime import PortRuntime
feat(#160): wire claw list-sessions and delete-session CLI commands Closes the last #160 gap: claws can now manage session lifecycle entirely through the CLI without filesystem hacks. New commands: - claw list-sessions [--directory DIR] [--output-format text|json] Enumerates stored session IDs. JSON mode emits {sessions, count}. Missing/empty directories return empty list (exit 0), not an error. - claw delete-session SESSION_ID [--directory DIR] [--output-format text|json] Idempotent: not-found is exit 0 with status='not_found' (no raise). Partial-failure: exit 1 with typed JSON error envelope: {session_id, deleted: false, error: {kind, message, retryable}} The 'session_delete_failed' kind is retryable=true so orchestrators know to retry vs escalate. Public API surface extended in src/__init__.py: - list_sessions, session_exists, delete_session - SessionNotFoundError, SessionDeleteError Tests added (tests/test_porting_workspace.py): - test_list_sessions_cli_runs: text + json modes against tempdir - test_delete_session_cli_idempotent: first call deleted=true, second call deleted=false (exit 0, status=not_found) - test_delete_session_cli_partial_failure_exit_1: permission error surfaces as exit 1 + typed JSON error with retryable=true All 43 tests pass. The session storage abstraction chapter is closed: - storage layer decoupled from claw code (#160 initial impl) - delete contract hardened + caller-audited (#160 hardening pass) - CLI wired with idempotency preserved at exit-code boundary (this commit)
2026-04-22 17:16:53 +09:00
from .session_store import (
SessionDeleteError,
SessionNotFoundError,
delete_session,
list_sessions,
load_session,
session_exists,
)
from .setup import run_setup
from .tool_pool import assemble_tool_pool
from .tools import execute_tool, get_tool, get_tools, render_tool_index
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(description='Python porting workspace for the Claude Code rewrite effort')
subparsers = parser.add_subparsers(dest='command', required=True)
subparsers.add_parser('summary', help='render a Markdown summary of the Python porting workspace')
subparsers.add_parser('manifest', help='print the current Python workspace manifest')
subparsers.add_parser('parity-audit', help='compare the Python workspace against the local ignored TypeScript archive when available')
subparsers.add_parser('setup-report', help='render the startup/prefetch setup report')
subparsers.add_parser('command-graph', help='show command graph segmentation')
subparsers.add_parser('tool-pool', help='show assembled tool pool with default settings')
subparsers.add_parser('bootstrap-graph', help='show the mirrored bootstrap/runtime graph stages')
list_parser = subparsers.add_parser('subsystems', help='list the current Python modules in the workspace')
list_parser.add_argument('--limit', type=int, default=32)
commands_parser = subparsers.add_parser('commands', help='list mirrored command entries from the archived snapshot')
commands_parser.add_argument('--limit', type=int, default=20)
commands_parser.add_argument('--query')
commands_parser.add_argument('--no-plugin-commands', action='store_true')
commands_parser.add_argument('--no-skill-commands', action='store_true')
tools_parser = subparsers.add_parser('tools', help='list mirrored tool entries from the archived snapshot')
tools_parser.add_argument('--limit', type=int, default=20)
tools_parser.add_argument('--query')
tools_parser.add_argument('--simple-mode', action='store_true')
tools_parser.add_argument('--no-mcp', action='store_true')
tools_parser.add_argument('--deny-tool', action='append', default=[])
tools_parser.add_argument('--deny-prefix', action='append', default=[])
route_parser = subparsers.add_parser('route', help='route a prompt across mirrored command/tool inventories')
route_parser.add_argument('prompt')
route_parser.add_argument('--limit', type=int, default=5)
bootstrap_parser = subparsers.add_parser('bootstrap', help='build a runtime-style session report from the mirrored inventories')
bootstrap_parser.add_argument('prompt')
bootstrap_parser.add_argument('--limit', type=int, default=5)
loop_parser = subparsers.add_parser('turn-loop', help='run a small stateful turn loop for the mirrored runtime')
loop_parser.add_argument('prompt')
loop_parser.add_argument('--limit', type=int, default=5)
loop_parser.add_argument('--max-turns', type=int, default=3)
loop_parser.add_argument('--structured-output', action='store_true')
fix: #161 — wall-clock timeout for run_turn_loop; stalled turns now abort with stop_reason='timeout' Previously, run_turn_loop was bounded only by max_turns (turn count). If engine.submit_message stalled — slow provider, hung network, infinite stream — the loop blocked indefinitely with no cancellation path. Claws calling run_turn_loop in CI or orchestration had no reliable way to enforce a deadline; the loop would hang until OS kill or human intervention. Fix: - Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded). - When set, each submit_message call runs inside a ThreadPoolExecutor and is bounded by the remaining wall-clock budget (total across all turns, not per-turn). - On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the turn's prompt and routed matches so transcripts preserve orchestration context. - Exhausted/negative budget short-circuits before calling submit_message. - Legacy path (timeout_seconds=None) bypasses the executor entirely — zero overhead for callers that don't opt in. CLI: - Added --timeout-seconds flag to 'turn-loop' command. - Exit code 2 when the loop terminated on timeout (vs 0 for completed), so shell scripts can distinguish 'done' from 'budget exhausted'. Tests (tests/test_run_turn_loop_timeout.py, 6 tests): - Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout') - Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s) - Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn) - timeout_seconds=0 short-circuits first turn without calling submit_message - Negative timeout treated as exhausted (guard against caller bugs) - Timeout TurnResult carries correct prompt, matches, UsageSummary shape Full suite: 49/49 passing, zero regression. Blocker: none. Closes ROADMAP #161.
2026-04-22 17:23:43 +09:00
loop_parser.add_argument(
'--timeout-seconds',
type=float,
default=None,
help='total wall-clock budget across all turns (#161). Default: unbounded.',
)
fix: #163 — remove [turn N] suffix pollution from run_turn_loop; file #164 timeout-cancellation followup #163: run_turn_loop no longer injects f'{prompt} [turn N]' into follow-up prompts. The suffix was never defined or interpreted anywhere — not by the engine, not by the system prompt, not by any LLM. It looked like a real user-typed annotation in the transcript and made replay/analysis fragile. New behaviour: - turn 0 submits the original prompt (unchanged) - turn > 0 submits caller-supplied continuation_prompt if provided, else the loop stops cleanly — no fabricated user turn - added continuation_prompt: str | None = None parameter to run_turn_loop - added --continuation-prompt CLI flag for claws scripting multi-turn loops - zero '[turn' strings ever appear in mutable_messages or stdout now Behaviour change for existing callers: - Before: run_turn_loop(prompt, max_turns=3) submitted 3 turns ('prompt', 'prompt [turn 2]', 'prompt [turn 3]') - After: run_turn_loop(prompt, max_turns=3) submits 1 turn ('prompt') - To preserve old multi-turn behaviour, pass continuation_prompt='Continue.' or any structured follow-up text One existing timeout test (test_budget_is_cumulative_across_turns) updated to pass continuation_prompt so the cumulative-budget contract is actually exercised across turns instead of trivially satisfied by a one-turn loop. #164 filed: addresses reviewer feedback on #161. The wall-clock timeout bounds the caller-facing wait, but the underlying submit_message worker thread keeps running and can mutate engine state after the timeout TurnResult is returned. A cooperative cancel_event pattern is sketched in the pinpoint; real asyncio.Task.cancel() support will come once provider IO is async-native (larger refactor). Tests (tests/test_run_turn_loop_continuation.py, 8 tests): - TestNoTurnSuffixInjection (2): zero '[turn' strings in any submitted prompt, both default and explicit-continuation paths - TestContinuationDefaultStopsAfterTurnZero (2): default loops run exactly one turn; engine.submit_message called exactly once despite max_turns=10 - TestExplicitContinuationBehaviour (2): turn 0 = original, turn N = continuation verbatim; max_turns still respected - TestCLIContinuationFlag (2): CLI default emits only '## Turn 1'; --continuation-prompt wires through to multi-turn behaviour Full suite: 67/67 passing. Closes ROADMAP #163. Files #164.
2026-04-22 17:37:22 +09:00
loop_parser.add_argument(
'--continuation-prompt',
default=None,
help=(
'prompt to submit on turns after the first (#163). Default: None '
'(loop stops after turn 0). Replaces the deprecated implicit "[turn N]" '
'suffix that used to pollute the transcript.'
),
)
flush_parser = subparsers.add_parser('flush-transcript', help='persist and flush a temporary session transcript')
flush_parser.add_argument('prompt')
fix: #165 — load-session CLI now parity-matches list/delete (--directory, --output-format, typed JSON errors) The #160 session-lifecycle CLI triplet was asymmetric: list-sessions and delete-session accepted --directory + --output-format and emitted typed JSON error envelopes, but load-session had neither flag and dumped a raw Python traceback (including the SessionNotFoundError class name) on a missing session. Three concrete impacts this fix closes: 1. Alternate session-store locations (e.g. /tmp/claw-run-XXX/.port_sessions) were unreachable via load-session; claws had to chdir or monkeypatch DEFAULT_SESSION_DIR to work around it. 2. Not-found emitted a multi-line Python stack, not a parseable envelope. Claws deciding retry/escalate/give-up had only exit code 1 to work with. 3. The traceback leaked 'src.session_store.SessionNotFoundError' verbatim, coupling version-pinned claws to our internal exception class name. Now all three triplet commands accept the same flag pair and emit the same JSON error shape: Success (json mode): {"session_id": "alpha", "loaded": true, "messages_count": 3, "input_tokens": 42, "output_tokens": 99} Not-found: {"session_id": "missing", "loaded": false, "error": {"kind": "session_not_found", "message": "session 'missing' not found in /path", "directory": "/path", "retryable": false}} Corrupted file: {"session_id": "broken", "loaded": false, "error": {"kind": "session_load_failed", "message": "...", "directory": "/path", "retryable": true}} Exit code contract: - 0 on successful load - 1 on not-found (preserves existing $?) - 1 on OSError/JSONDecodeError (distinct 'kind' in JSON) Backward compat: legacy 'claw load-session ID' text output unchanged byte-for-byte. Only new behaviour is the flags and structured error path. Tests (tests/test_load_session_cli.py, 13 tests): - TestDirectoryFlagParity (2): --directory works + fallback to CWD/.port_sessions - TestOutputFormatFlagParity (2): json schema + text-mode backward compat - TestNotFoundTypedError (2): JSON envelope on not-found; no traceback in either mode; no internal class name leak - TestLoadFailedDistinctFromNotFound (1): corrupted file = session_load_failed with retryable=true, distinct from session_not_found - TestTripletParityConsistency (6): parametrised over [list, delete, load] * [--directory, --output-format] — explicit parity guard for future regressions Full suite: 80/80 passing, zero regression. Discovered via Jobdori dogfood sweep 2026-04-22 17:44 KST — ran 'claw load-session nonexistent' expecting a clean error, got a Python traceback. Filed #165 + fixed in same commit. Closes ROADMAP #165.
2026-04-22 17:44:48 +09:00
load_session_parser = subparsers.add_parser(
'load-session',
help='load a previously persisted session (#160/#165: claw-native session API)',
)
load_session_parser.add_argument('session_id')
fix: #165 — load-session CLI now parity-matches list/delete (--directory, --output-format, typed JSON errors) The #160 session-lifecycle CLI triplet was asymmetric: list-sessions and delete-session accepted --directory + --output-format and emitted typed JSON error envelopes, but load-session had neither flag and dumped a raw Python traceback (including the SessionNotFoundError class name) on a missing session. Three concrete impacts this fix closes: 1. Alternate session-store locations (e.g. /tmp/claw-run-XXX/.port_sessions) were unreachable via load-session; claws had to chdir or monkeypatch DEFAULT_SESSION_DIR to work around it. 2. Not-found emitted a multi-line Python stack, not a parseable envelope. Claws deciding retry/escalate/give-up had only exit code 1 to work with. 3. The traceback leaked 'src.session_store.SessionNotFoundError' verbatim, coupling version-pinned claws to our internal exception class name. Now all three triplet commands accept the same flag pair and emit the same JSON error shape: Success (json mode): {"session_id": "alpha", "loaded": true, "messages_count": 3, "input_tokens": 42, "output_tokens": 99} Not-found: {"session_id": "missing", "loaded": false, "error": {"kind": "session_not_found", "message": "session 'missing' not found in /path", "directory": "/path", "retryable": false}} Corrupted file: {"session_id": "broken", "loaded": false, "error": {"kind": "session_load_failed", "message": "...", "directory": "/path", "retryable": true}} Exit code contract: - 0 on successful load - 1 on not-found (preserves existing $?) - 1 on OSError/JSONDecodeError (distinct 'kind' in JSON) Backward compat: legacy 'claw load-session ID' text output unchanged byte-for-byte. Only new behaviour is the flags and structured error path. Tests (tests/test_load_session_cli.py, 13 tests): - TestDirectoryFlagParity (2): --directory works + fallback to CWD/.port_sessions - TestOutputFormatFlagParity (2): json schema + text-mode backward compat - TestNotFoundTypedError (2): JSON envelope on not-found; no traceback in either mode; no internal class name leak - TestLoadFailedDistinctFromNotFound (1): corrupted file = session_load_failed with retryable=true, distinct from session_not_found - TestTripletParityConsistency (6): parametrised over [list, delete, load] * [--directory, --output-format] — explicit parity guard for future regressions Full suite: 80/80 passing, zero regression. Discovered via Jobdori dogfood sweep 2026-04-22 17:44 KST — ran 'claw load-session nonexistent' expecting a clean error, got a Python traceback. Filed #165 + fixed in same commit. Closes ROADMAP #165.
2026-04-22 17:44:48 +09:00
load_session_parser.add_argument(
'--directory', help='session storage directory (default: .port_sessions)'
)
load_session_parser.add_argument(
'--output-format',
choices=['text', 'json'],
default='text',
help='output format',
)
feat(#160): wire claw list-sessions and delete-session CLI commands Closes the last #160 gap: claws can now manage session lifecycle entirely through the CLI without filesystem hacks. New commands: - claw list-sessions [--directory DIR] [--output-format text|json] Enumerates stored session IDs. JSON mode emits {sessions, count}. Missing/empty directories return empty list (exit 0), not an error. - claw delete-session SESSION_ID [--directory DIR] [--output-format text|json] Idempotent: not-found is exit 0 with status='not_found' (no raise). Partial-failure: exit 1 with typed JSON error envelope: {session_id, deleted: false, error: {kind, message, retryable}} The 'session_delete_failed' kind is retryable=true so orchestrators know to retry vs escalate. Public API surface extended in src/__init__.py: - list_sessions, session_exists, delete_session - SessionNotFoundError, SessionDeleteError Tests added (tests/test_porting_workspace.py): - test_list_sessions_cli_runs: text + json modes against tempdir - test_delete_session_cli_idempotent: first call deleted=true, second call deleted=false (exit 0, status=not_found) - test_delete_session_cli_partial_failure_exit_1: permission error surfaces as exit 1 + typed JSON error with retryable=true All 43 tests pass. The session storage abstraction chapter is closed: - storage layer decoupled from claw code (#160 initial impl) - delete contract hardened + caller-audited (#160 hardening pass) - CLI wired with idempotency preserved at exit-code boundary (this commit)
2026-04-22 17:16:53 +09:00
list_sessions_parser = subparsers.add_parser(
'list-sessions',
help='enumerate stored session IDs (#160: claw-native session API)',
)
list_sessions_parser.add_argument(
'--directory', help='session storage directory (default: .port_sessions)'
)
list_sessions_parser.add_argument(
'--output-format',
choices=['text', 'json'],
default='text',
help='output format',
)
delete_session_parser = subparsers.add_parser(
'delete-session',
help='delete a persisted session (#160: idempotent, race-safe)',
)
delete_session_parser.add_argument('session_id')
delete_session_parser.add_argument(
'--directory', help='session storage directory (default: .port_sessions)'
)
delete_session_parser.add_argument(
'--output-format',
choices=['text', 'json'],
default='text',
help='output format',
)
remote_parser = subparsers.add_parser('remote-mode', help='simulate remote-control runtime branching')
remote_parser.add_argument('target')
ssh_parser = subparsers.add_parser('ssh-mode', help='simulate SSH runtime branching')
ssh_parser.add_argument('target')
teleport_parser = subparsers.add_parser('teleport-mode', help='simulate teleport runtime branching')
teleport_parser.add_argument('target')
direct_parser = subparsers.add_parser('direct-connect-mode', help='simulate direct-connect runtime branching')
direct_parser.add_argument('target')
deep_link_parser = subparsers.add_parser('deep-link-mode', help='simulate deep-link runtime branching')
deep_link_parser.add_argument('target')
show_command = subparsers.add_parser('show-command', help='show one mirrored command entry by exact name')
show_command.add_argument('name')
show_tool = subparsers.add_parser('show-tool', help='show one mirrored tool entry by exact name')
show_tool.add_argument('name')
exec_command_parser = subparsers.add_parser('exec-command', help='execute a mirrored command shim by exact name')
exec_command_parser.add_argument('name')
exec_command_parser.add_argument('prompt')
exec_tool_parser = subparsers.add_parser('exec-tool', help='execute a mirrored tool shim by exact name')
exec_tool_parser.add_argument('name')
exec_tool_parser.add_argument('payload')
return parser
def main(argv: list[str] | None = None) -> int:
parser = build_parser()
args = parser.parse_args(argv)
manifest = build_port_manifest()
if args.command == 'summary':
print(QueryEnginePort(manifest).render_summary())
return 0
if args.command == 'manifest':
print(manifest.to_markdown())
return 0
if args.command == 'parity-audit':
print(run_parity_audit().to_markdown())
return 0
if args.command == 'setup-report':
print(run_setup().as_markdown())
return 0
if args.command == 'command-graph':
print(build_command_graph().as_markdown())
return 0
if args.command == 'tool-pool':
print(assemble_tool_pool().as_markdown())
return 0
if args.command == 'bootstrap-graph':
print(build_bootstrap_graph().as_markdown())
return 0
if args.command == 'subsystems':
for subsystem in manifest.top_level_modules[: args.limit]:
print(f'{subsystem.name}\t{subsystem.file_count}\t{subsystem.notes}')
return 0
if args.command == 'commands':
if args.query:
print(render_command_index(limit=args.limit, query=args.query))
else:
commands = get_commands(include_plugin_commands=not args.no_plugin_commands, include_skill_commands=not args.no_skill_commands)
output_lines = [f'Command entries: {len(commands)}', '']
output_lines.extend(f'- {module.name}{module.source_hint}' for module in commands[: args.limit])
print('\n'.join(output_lines))
return 0
if args.command == 'tools':
if args.query:
print(render_tool_index(limit=args.limit, query=args.query))
else:
permission_context = ToolPermissionContext.from_iterables(args.deny_tool, args.deny_prefix)
tools = get_tools(simple_mode=args.simple_mode, include_mcp=not args.no_mcp, permission_context=permission_context)
output_lines = [f'Tool entries: {len(tools)}', '']
output_lines.extend(f'- {module.name}{module.source_hint}' for module in tools[: args.limit])
print('\n'.join(output_lines))
return 0
if args.command == 'route':
matches = PortRuntime().route_prompt(args.prompt, limit=args.limit)
if not matches:
print('No mirrored command/tool matches found.')
return 0
for match in matches:
print(f'{match.kind}\t{match.name}\t{match.score}\t{match.source_hint}')
return 0
if args.command == 'bootstrap':
print(PortRuntime().bootstrap_session(args.prompt, limit=args.limit).as_markdown())
return 0
if args.command == 'turn-loop':
fix: #161 — wall-clock timeout for run_turn_loop; stalled turns now abort with stop_reason='timeout' Previously, run_turn_loop was bounded only by max_turns (turn count). If engine.submit_message stalled — slow provider, hung network, infinite stream — the loop blocked indefinitely with no cancellation path. Claws calling run_turn_loop in CI or orchestration had no reliable way to enforce a deadline; the loop would hang until OS kill or human intervention. Fix: - Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded). - When set, each submit_message call runs inside a ThreadPoolExecutor and is bounded by the remaining wall-clock budget (total across all turns, not per-turn). - On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the turn's prompt and routed matches so transcripts preserve orchestration context. - Exhausted/negative budget short-circuits before calling submit_message. - Legacy path (timeout_seconds=None) bypasses the executor entirely — zero overhead for callers that don't opt in. CLI: - Added --timeout-seconds flag to 'turn-loop' command. - Exit code 2 when the loop terminated on timeout (vs 0 for completed), so shell scripts can distinguish 'done' from 'budget exhausted'. Tests (tests/test_run_turn_loop_timeout.py, 6 tests): - Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout') - Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s) - Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn) - timeout_seconds=0 short-circuits first turn without calling submit_message - Negative timeout treated as exhausted (guard against caller bugs) - Timeout TurnResult carries correct prompt, matches, UsageSummary shape Full suite: 49/49 passing, zero regression. Blocker: none. Closes ROADMAP #161.
2026-04-22 17:23:43 +09:00
results = PortRuntime().run_turn_loop(
args.prompt,
limit=args.limit,
max_turns=args.max_turns,
structured_output=args.structured_output,
timeout_seconds=args.timeout_seconds,
fix: #163 — remove [turn N] suffix pollution from run_turn_loop; file #164 timeout-cancellation followup #163: run_turn_loop no longer injects f'{prompt} [turn N]' into follow-up prompts. The suffix was never defined or interpreted anywhere — not by the engine, not by the system prompt, not by any LLM. It looked like a real user-typed annotation in the transcript and made replay/analysis fragile. New behaviour: - turn 0 submits the original prompt (unchanged) - turn > 0 submits caller-supplied continuation_prompt if provided, else the loop stops cleanly — no fabricated user turn - added continuation_prompt: str | None = None parameter to run_turn_loop - added --continuation-prompt CLI flag for claws scripting multi-turn loops - zero '[turn' strings ever appear in mutable_messages or stdout now Behaviour change for existing callers: - Before: run_turn_loop(prompt, max_turns=3) submitted 3 turns ('prompt', 'prompt [turn 2]', 'prompt [turn 3]') - After: run_turn_loop(prompt, max_turns=3) submits 1 turn ('prompt') - To preserve old multi-turn behaviour, pass continuation_prompt='Continue.' or any structured follow-up text One existing timeout test (test_budget_is_cumulative_across_turns) updated to pass continuation_prompt so the cumulative-budget contract is actually exercised across turns instead of trivially satisfied by a one-turn loop. #164 filed: addresses reviewer feedback on #161. The wall-clock timeout bounds the caller-facing wait, but the underlying submit_message worker thread keeps running and can mutate engine state after the timeout TurnResult is returned. A cooperative cancel_event pattern is sketched in the pinpoint; real asyncio.Task.cancel() support will come once provider IO is async-native (larger refactor). Tests (tests/test_run_turn_loop_continuation.py, 8 tests): - TestNoTurnSuffixInjection (2): zero '[turn' strings in any submitted prompt, both default and explicit-continuation paths - TestContinuationDefaultStopsAfterTurnZero (2): default loops run exactly one turn; engine.submit_message called exactly once despite max_turns=10 - TestExplicitContinuationBehaviour (2): turn 0 = original, turn N = continuation verbatim; max_turns still respected - TestCLIContinuationFlag (2): CLI default emits only '## Turn 1'; --continuation-prompt wires through to multi-turn behaviour Full suite: 67/67 passing. Closes ROADMAP #163. Files #164.
2026-04-22 17:37:22 +09:00
continuation_prompt=args.continuation_prompt,
fix: #161 — wall-clock timeout for run_turn_loop; stalled turns now abort with stop_reason='timeout' Previously, run_turn_loop was bounded only by max_turns (turn count). If engine.submit_message stalled — slow provider, hung network, infinite stream — the loop blocked indefinitely with no cancellation path. Claws calling run_turn_loop in CI or orchestration had no reliable way to enforce a deadline; the loop would hang until OS kill or human intervention. Fix: - Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded). - When set, each submit_message call runs inside a ThreadPoolExecutor and is bounded by the remaining wall-clock budget (total across all turns, not per-turn). - On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the turn's prompt and routed matches so transcripts preserve orchestration context. - Exhausted/negative budget short-circuits before calling submit_message. - Legacy path (timeout_seconds=None) bypasses the executor entirely — zero overhead for callers that don't opt in. CLI: - Added --timeout-seconds flag to 'turn-loop' command. - Exit code 2 when the loop terminated on timeout (vs 0 for completed), so shell scripts can distinguish 'done' from 'budget exhausted'. Tests (tests/test_run_turn_loop_timeout.py, 6 tests): - Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout') - Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s) - Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn) - timeout_seconds=0 short-circuits first turn without calling submit_message - Negative timeout treated as exhausted (guard against caller bugs) - Timeout TurnResult carries correct prompt, matches, UsageSummary shape Full suite: 49/49 passing, zero regression. Blocker: none. Closes ROADMAP #161.
2026-04-22 17:23:43 +09:00
)
for idx, result in enumerate(results, start=1):
print(f'## Turn {idx}')
print(result.output)
print(f'stop_reason={result.stop_reason}')
fix: #161 — wall-clock timeout for run_turn_loop; stalled turns now abort with stop_reason='timeout' Previously, run_turn_loop was bounded only by max_turns (turn count). If engine.submit_message stalled — slow provider, hung network, infinite stream — the loop blocked indefinitely with no cancellation path. Claws calling run_turn_loop in CI or orchestration had no reliable way to enforce a deadline; the loop would hang until OS kill or human intervention. Fix: - Add timeout_seconds parameter to run_turn_loop (default None = legacy unbounded). - When set, each submit_message call runs inside a ThreadPoolExecutor and is bounded by the remaining wall-clock budget (total across all turns, not per-turn). - On timeout, synthesize a TurnResult with stop_reason='timeout' carrying the turn's prompt and routed matches so transcripts preserve orchestration context. - Exhausted/negative budget short-circuits before calling submit_message. - Legacy path (timeout_seconds=None) bypasses the executor entirely — zero overhead for callers that don't opt in. CLI: - Added --timeout-seconds flag to 'turn-loop' command. - Exit code 2 when the loop terminated on timeout (vs 0 for completed), so shell scripts can distinguish 'done' from 'budget exhausted'. Tests (tests/test_run_turn_loop_timeout.py, 6 tests): - Legacy unbounded path unchanged (timeout_seconds=None never emits 'timeout') - Hung submit_message aborted within budget (0.3s budget, 5s mock hang → exit <1.5s) - Budget is cumulative across turns (0.6s budget, 0.4s per turn, not per-turn) - timeout_seconds=0 short-circuits first turn without calling submit_message - Negative timeout treated as exhausted (guard against caller bugs) - Timeout TurnResult carries correct prompt, matches, UsageSummary shape Full suite: 49/49 passing, zero regression. Blocker: none. Closes ROADMAP #161.
2026-04-22 17:23:43 +09:00
# Exit 2 when a timeout terminated the loop so claws can distinguish
# 'ran to completion' from 'hit wall-clock budget'.
if results and results[-1].stop_reason == 'timeout':
return 2
return 0
if args.command == 'flush-transcript':
engine = QueryEnginePort.from_workspace()
engine.submit_message(args.prompt)
path = engine.persist_session()
print(path)
print(f'flushed={engine.transcript_store.flushed}')
return 0
if args.command == 'load-session':
fix: #165 — load-session CLI now parity-matches list/delete (--directory, --output-format, typed JSON errors) The #160 session-lifecycle CLI triplet was asymmetric: list-sessions and delete-session accepted --directory + --output-format and emitted typed JSON error envelopes, but load-session had neither flag and dumped a raw Python traceback (including the SessionNotFoundError class name) on a missing session. Three concrete impacts this fix closes: 1. Alternate session-store locations (e.g. /tmp/claw-run-XXX/.port_sessions) were unreachable via load-session; claws had to chdir or monkeypatch DEFAULT_SESSION_DIR to work around it. 2. Not-found emitted a multi-line Python stack, not a parseable envelope. Claws deciding retry/escalate/give-up had only exit code 1 to work with. 3. The traceback leaked 'src.session_store.SessionNotFoundError' verbatim, coupling version-pinned claws to our internal exception class name. Now all three triplet commands accept the same flag pair and emit the same JSON error shape: Success (json mode): {"session_id": "alpha", "loaded": true, "messages_count": 3, "input_tokens": 42, "output_tokens": 99} Not-found: {"session_id": "missing", "loaded": false, "error": {"kind": "session_not_found", "message": "session 'missing' not found in /path", "directory": "/path", "retryable": false}} Corrupted file: {"session_id": "broken", "loaded": false, "error": {"kind": "session_load_failed", "message": "...", "directory": "/path", "retryable": true}} Exit code contract: - 0 on successful load - 1 on not-found (preserves existing $?) - 1 on OSError/JSONDecodeError (distinct 'kind' in JSON) Backward compat: legacy 'claw load-session ID' text output unchanged byte-for-byte. Only new behaviour is the flags and structured error path. Tests (tests/test_load_session_cli.py, 13 tests): - TestDirectoryFlagParity (2): --directory works + fallback to CWD/.port_sessions - TestOutputFormatFlagParity (2): json schema + text-mode backward compat - TestNotFoundTypedError (2): JSON envelope on not-found; no traceback in either mode; no internal class name leak - TestLoadFailedDistinctFromNotFound (1): corrupted file = session_load_failed with retryable=true, distinct from session_not_found - TestTripletParityConsistency (6): parametrised over [list, delete, load] * [--directory, --output-format] — explicit parity guard for future regressions Full suite: 80/80 passing, zero regression. Discovered via Jobdori dogfood sweep 2026-04-22 17:44 KST — ran 'claw load-session nonexistent' expecting a clean error, got a Python traceback. Filed #165 + fixed in same commit. Closes ROADMAP #165.
2026-04-22 17:44:48 +09:00
from pathlib import Path as _Path
directory = _Path(args.directory) if args.directory else None
# #165: catch typed SessionNotFoundError + surface a JSON error envelope
# matching the delete-session contract shape. No more raw tracebacks.
try:
session = load_session(args.session_id, directory)
except SessionNotFoundError as exc:
if args.output_format == 'json':
import json as _json
resolved_dir = str(directory) if directory else '.port_sessions'
print(_json.dumps({
'session_id': args.session_id,
'loaded': False,
'error': {
'kind': 'session_not_found',
'message': str(exc),
'directory': resolved_dir,
'retryable': False,
},
}))
else:
print(f'error: {exc}')
return 1
except (OSError, ValueError) as exc:
# Corrupted session file, IO error, JSON decode error — distinct
# from 'not found'. Callers may retry here (fs glitch).
if args.output_format == 'json':
import json as _json
resolved_dir = str(directory) if directory else '.port_sessions'
print(_json.dumps({
'session_id': args.session_id,
'loaded': False,
'error': {
'kind': 'session_load_failed',
'message': str(exc),
'directory': resolved_dir,
'retryable': True,
},
}))
else:
print(f'error: {exc}')
return 1
if args.output_format == 'json':
import json as _json
print(_json.dumps({
'session_id': session.session_id,
'loaded': True,
'messages_count': len(session.messages),
'input_tokens': session.input_tokens,
'output_tokens': session.output_tokens,
}))
else:
print(f'{session.session_id}\n{len(session.messages)} messages\nin={session.input_tokens} out={session.output_tokens}')
return 0
feat(#160): wire claw list-sessions and delete-session CLI commands Closes the last #160 gap: claws can now manage session lifecycle entirely through the CLI without filesystem hacks. New commands: - claw list-sessions [--directory DIR] [--output-format text|json] Enumerates stored session IDs. JSON mode emits {sessions, count}. Missing/empty directories return empty list (exit 0), not an error. - claw delete-session SESSION_ID [--directory DIR] [--output-format text|json] Idempotent: not-found is exit 0 with status='not_found' (no raise). Partial-failure: exit 1 with typed JSON error envelope: {session_id, deleted: false, error: {kind, message, retryable}} The 'session_delete_failed' kind is retryable=true so orchestrators know to retry vs escalate. Public API surface extended in src/__init__.py: - list_sessions, session_exists, delete_session - SessionNotFoundError, SessionDeleteError Tests added (tests/test_porting_workspace.py): - test_list_sessions_cli_runs: text + json modes against tempdir - test_delete_session_cli_idempotent: first call deleted=true, second call deleted=false (exit 0, status=not_found) - test_delete_session_cli_partial_failure_exit_1: permission error surfaces as exit 1 + typed JSON error with retryable=true All 43 tests pass. The session storage abstraction chapter is closed: - storage layer decoupled from claw code (#160 initial impl) - delete contract hardened + caller-audited (#160 hardening pass) - CLI wired with idempotency preserved at exit-code boundary (this commit)
2026-04-22 17:16:53 +09:00
if args.command == 'list-sessions':
from pathlib import Path as _Path
directory = _Path(args.directory) if args.directory else None
ids = list_sessions(directory)
if args.output_format == 'json':
import json as _json
print(_json.dumps({'sessions': ids, 'count': len(ids)}))
else:
if not ids:
print('(no sessions)')
else:
for sid in ids:
print(sid)
return 0
if args.command == 'delete-session':
from pathlib import Path as _Path
directory = _Path(args.directory) if args.directory else None
try:
deleted = delete_session(args.session_id, directory)
except SessionDeleteError as exc:
if args.output_format == 'json':
import json as _json
print(_json.dumps({
'session_id': args.session_id,
'deleted': False,
'error': {
'kind': 'session_delete_failed',
'message': str(exc),
'retryable': True,
},
}))
else:
print(f'error: {exc}')
return 1
if args.output_format == 'json':
import json as _json
print(_json.dumps({
'session_id': args.session_id,
'deleted': deleted,
'status': 'deleted' if deleted else 'not_found',
}))
else:
if deleted:
print(f'deleted: {args.session_id}')
else:
print(f'not found: {args.session_id}')
# Exit 0 for both cases — delete_session is idempotent,
# not-found is success from a cleanup perspective
return 0
if args.command == 'remote-mode':
print(run_remote_mode(args.target).as_text())
return 0
if args.command == 'ssh-mode':
print(run_ssh_mode(args.target).as_text())
return 0
if args.command == 'teleport-mode':
print(run_teleport_mode(args.target).as_text())
return 0
if args.command == 'direct-connect-mode':
print(run_direct_connect(args.target).as_text())
return 0
if args.command == 'deep-link-mode':
print(run_deep_link(args.target).as_text())
return 0
if args.command == 'show-command':
module = get_command(args.name)
if module is None:
print(f'Command not found: {args.name}')
return 1
print('\n'.join([module.name, module.source_hint, module.responsibility]))
return 0
if args.command == 'show-tool':
module = get_tool(args.name)
if module is None:
print(f'Tool not found: {args.name}')
return 1
print('\n'.join([module.name, module.source_hint, module.responsibility]))
return 0
if args.command == 'exec-command':
result = execute_command(args.name, args.prompt)
print(result.message)
return 0 if result.handled else 1
if args.command == 'exec-tool':
result = execute_tool(args.name, args.payload)
print(result.message)
return 0 if result.handled else 1
parser.error(f'unknown command: {args.command}')
return 2
if __name__ == '__main__':
raise SystemExit(main())